From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2F09A282E1; Tue, 12 Aug 2025 18:21:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1755022865; cv=none; b=t/NdIecUTIXNYP62q4l9KgHleuCYkNSnm5ZLeVZ+5pYUr9brYsTFwRQVzWTlaeET+DIuajzByghAlnVGerkrnSal9f3oWBmzPV5ZVifVM/42t1gnrTR8ZXdBLBVTjNO+FlcL5p1aTrM8Mpj6LSe3Xlg4s4llVmHLmVtMmqpwC28= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1755022865; c=relaxed/simple; bh=tdazR0vCepjLSQBzhIH1rD+QCN+P3pXG2r/oUh6EdO0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=UFUk7VsUp0usEtLmt8ueI7sSLEQavAf0vwfJzJliLYvkt5QpPNZlWVgH8dBSWdPxnQ5lK5MMaiq4VCcmRyPQOEr/x0ezaocL2OsUQJKZYO+OMJaXxRyT9V7CgA5FCaOhVRlACccShF6lcWeM15l+CQqE/kUy66s4XBBa4azNTZg= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=DfUgQdK9; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b="DfUgQdK9" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 3F4CFC4CEF1; Tue, 12 Aug 2025 18:21:04 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1755022864; bh=tdazR0vCepjLSQBzhIH1rD+QCN+P3pXG2r/oUh6EdO0=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=DfUgQdK9U10hoynOhoIsroG2CREzntbc6MCdvni65yBR90Ygwc5au3wVF1ecJJQ5/ 3b5cJNx8VOzwya2Eu21HN4R9P2W0RnucaJPGTm04mNK1usl6v70Hj7e4Y6h4+UYzVA ssZEcyNzRCPFDVTS3hs3njDECSDjZzqL6gxyU8RU= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, Tigran Mkrtchyan , Trond Myklebust , Sasha Levin Subject: [PATCH 6.12 280/369] pNFS/flexfiles: dont attempt pnfs on fatal DS errors Date: Tue, 12 Aug 2025 19:29:37 +0200 Message-ID: <20250812173026.662405881@linuxfoundation.org> X-Mailer: git-send-email 2.50.1 In-Reply-To: <20250812173014.736537091@linuxfoundation.org> References: <20250812173014.736537091@linuxfoundation.org> User-Agent: quilt/0.68 X-stable: review X-Patchwork-Hint: ignore Precedence: bulk X-Mailing-List: patches@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 6.12-stable review patch. If anyone has any objections, please let me know. ------------------ From: Tigran Mkrtchyan [ Upstream commit f06bedfa62d57f7b67d44aacd6badad2e13a803f ] When an applications get killed (SIGTERM/SIGINT) while pNFS client performs a connection to DS, client ends in an infinite loop of connect-disconnect. This source of the issue, it that flexfilelayoutdev#nfs4_ff_layout_prepare_ds gets an error on nfs4_pnfs_ds_connect with status ERESTARTSYS, which is set by rpc_signal_task, but the error is treated as transient, thus retried. The issue is reproducible with Ctrl+C the following script(there should be ~1000 files in a directory, client should must not have any connections to DSes): ``` echo 3 > /proc/sys/vm/drop_caches for i in * do head -1 $i done ``` The change aims to propagate the nfs4_ff_layout_prepare_ds error state to the caller that can decide whatever this is a retryable error or not. Signed-off-by: Tigran Mkrtchyan Link: https://lore.kernel.org/r/20250627071751.189663-1-tigran.mkrtchyan@desy.de Fixes: 260f32adb88d ("pNFS/flexfiles: Check the result of nfs4_pnfs_ds_connect") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/flexfilelayout/flexfilelayout.c | 26 ++++++++++++++--------- fs/nfs/flexfilelayout/flexfilelayoutdev.c | 6 +++--- 2 files changed, 19 insertions(+), 13 deletions(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index bf96f7a8900c..b685e763ef11 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -761,14 +761,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, { struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_ff_layout_mirror *mirror; - struct nfs4_pnfs_ds *ds; + struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN); u32 idx; /* mirrors are initially sorted by efficiency */ for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false); - if (!ds) + if (IS_ERR(ds)) continue; if (check_device && @@ -776,10 +776,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, continue; *best_idx = idx; - return ds; + break; } - return NULL; + return ds; } static struct nfs4_pnfs_ds * @@ -941,7 +941,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, for (i = 0; i < pgio->pg_mirror_count; i++) { mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true); - if (!ds) { + if (IS_ERR(ds)) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; pnfs_generic_pg_cleanup(pgio); @@ -1848,6 +1848,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) u32 idx = hdr->pgio_mirror_idx; int vers; struct nfs_fh *fh; + bool ds_fatal_error = false; dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n", __func__, hdr->inode->i_ino, @@ -1855,8 +1856,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false); - if (!ds) + if (IS_ERR(ds)) { + ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds)); goto out_failed; + } ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp, hdr->inode); @@ -1904,7 +1907,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) return PNFS_ATTEMPTED; out_failed: - if (ff_layout_avoid_mds_available_ds(lseg)) + if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error) return PNFS_TRY_AGAIN; trace_pnfs_mds_fallback_read_pagelist(hdr->inode, hdr->args.offset, hdr->args.count, @@ -1926,11 +1929,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) int vers; struct nfs_fh *fh; u32 idx = hdr->pgio_mirror_idx; + bool ds_fatal_error = false; mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true); - if (!ds) + if (IS_ERR(ds)) { + ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds)); goto out_failed; + } ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp, hdr->inode); @@ -1981,7 +1987,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) return PNFS_ATTEMPTED; out_failed: - if (ff_layout_avoid_mds_available_ds(lseg)) + if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error) return PNFS_TRY_AGAIN; trace_pnfs_mds_fallback_write_pagelist(hdr->inode, hdr->args.offset, hdr->args.count, @@ -2024,7 +2030,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true); - if (!ds) + if (IS_ERR(ds)) goto out_err; ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp, diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 4a304cf17c4b..ef535baeefb6 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -370,11 +370,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, struct nfs4_ff_layout_mirror *mirror, bool fail_return) { - struct nfs4_pnfs_ds *ds = NULL; + struct nfs4_pnfs_ds *ds; struct inode *ino = lseg->pls_layout->plh_inode; struct nfs_server *s = NFS_SERVER(ino); unsigned int max_payload; - int status; + int status = -EAGAIN; if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror)) goto noconnect; @@ -418,7 +418,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, ff_layout_send_layouterror(lseg); if (fail_return || !ff_layout_has_available_ds(lseg)) pnfs_error_mark_layout_for_return(ino, lseg); - ds = NULL; + ds = ERR_PTR(status); out: return ds; } -- 2.39.5